gym-csle-stopping-game 0.8.0__tar.gz → 0.8.2__tar.gz

{gym_csle_stopping_game-0.8.0 → gym_csle_stopping_game-0.8.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-csle-stopping-game
-Version: 0.8.0
+Version: 0.8.2
 Summary: OpenAI gym reinforcement learning environment of a Dynkin (Optimal stopping) game in CSLE
 Author: Kim Hammar
 Author-email: hammar.kim@gmail.com
@@ -204,11 +204,11 @@ Classifier: Intended Audience :: Science/Research
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 Requires-Dist: gymnasium>=0.27.1
-Requires-Dist: csle-base>=0.8.0
-Requires-Dist: csle-common>=0.8.0
-Requires-Dist: csle-attacker>=0.8.0
-Requires-Dist: csle-defender>=0.8.0
-Requires-Dist: csle-collector>=0.8.0
+Requires-Dist: csle-base>=0.8.2
+Requires-Dist: csle-common>=0.8.2
+Requires-Dist: csle-attacker>=0.8.2
+Requires-Dist: csle-defender>=0.8.2
+Requires-Dist: csle-collector>=0.8.2
 Provides-Extra: test
 Requires-Dist: pytest>=6.0; extra == "test"
 Requires-Dist: pytest-cov>=2.0; extra == "test"
@@ -216,7 +216,7 @@ Requires-Dist: pytest-mock>=3.6.0; extra == "test"
 Requires-Dist: pytest-grpc>=0.8.0; extra == "test"
 Requires-Dist: grpcio>=1.69.0; extra == "test"
 Requires-Dist: grpcio-tools>=1.69.0; extra == "test"
-Requires-Dist: mypy>=1.4.1; extra == "test"
+Requires-Dist: mypy>=1.7.0; extra == "test"
 Requires-Dist: mypy-extensions>=1.0.0; extra == "test"
 Requires-Dist: mypy-protobuf>=3.5.0; extra == "test"
 Requires-Dist: types-PyYAML>=6.0.12.11; extra == "test"
@@ -226,11 +226,11 @@ Requires-Dist: types-requests>=2.31.0.1; extra == "test"
 Requires-Dist: types-urllib3>=1.26.25.13; extra == "test"
 Requires-Dist: flake8>=6.1.0; extra == "test"
 Requires-Dist: flake8-rst-docstrings>=0.3.0; extra == "test"
-Requires-Dist: tox>=3.24; extra == "test"
+Requires-Dist: tox>=4.24.1; extra == "test"
 Requires-Dist: sphinx>=5.3.0; extra == "test"
 Requires-Dist: sphinxcontrib-napoleon>=0.7; extra == "test"
 Requires-Dist: sphinx-rtd-theme>=1.1.1; extra == "test"
-Requires-Dist: twine>=4.0.2; extra == "test"
+Requires-Dist: twine>=6.1.0; extra == "test"
 Requires-Dist: build>=0.10.0; extra == "test"
 
 # `gym-csle-stopping-game`

{gym_csle_stopping_game-0.8.0 → gym_csle_stopping_game-0.8.2}/pyproject.toml

@@ -19,11 +19,11 @@ classifiers = [
 ]
 dependencies = [
     "gymnasium>=0.27.1",
-    "csle-base>=0.8.0",
-    "csle-common>=0.8.0",
-    "csle-attacker>=0.8.0",
-    "csle-defender>=0.8.0",
-    "csle-collector>=0.8.0"
+    "csle-base>=0.8.2",
+    "csle-common>=0.8.2",
+    "csle-attacker>=0.8.2",
+    "csle-defender>=0.8.2",
+    "csle-collector>=0.8.2"
 ]
 
 [project.optional-dependencies]
@@ -34,7 +34,7 @@ test = [
     "pytest-grpc>=0.8.0",
     "grpcio>=1.69.0",
     "grpcio-tools>=1.69.0",
-    "mypy>=1.4.1",
+    "mypy>=1.7.0",
     "mypy-extensions>=1.0.0",
     "mypy-protobuf>=3.5.0",
     "types-PyYAML>=6.0.12.11",
@@ -44,11 +44,11 @@ test = [
     "types-urllib3>=1.26.25.13",
     "flake8>=6.1.0",
     "flake8-rst-docstrings>=0.3.0",
-    "tox>=3.24",
+    "tox>=4.24.1",
     "sphinx>=5.3.0",
     "sphinxcontrib-napoleon>=0.7",
     "sphinx-rtd-theme>=1.1.1",
-    "twine>=4.0.2",
+    "twine>=6.1.0",
     "build>=0.10.0"
 ]
 
@@ -82,4 +82,8 @@ warn_redundant_casts = true
 warn_return_any = true
 warn_unreachable = true
 warn_unused_configs = true
-no_implicit_reexport = true
+no_implicit_reexport = true
+
+[[tool.mypy.overrides]]
+follow_imports = "skip"
+module = ["transformers.*"]

{gym_csle_stopping_game-0.8.0 → gym_csle_stopping_game-0.8.2}/setup.cfg

@@ -20,11 +20,11 @@ classifiers =
 [options]
 install_requires = 
 	gymnasium>=0.27.1
-	csle-base>=0.8.0
-	csle-common>=0.8.0
-	csle-attacker>=0.8.0
-	csle-defender>=0.8.0
-	csle-collector>=0.8.0
+	csle-base>=0.8.2
+	csle-common>=0.8.2
+	csle-attacker>=0.8.2
+	csle-defender>=0.8.2
+	csle-collector>=0.8.2
 python_requires = >=3.8
 package_dir = 
 	=src
@@ -42,7 +42,7 @@ testing =
 	grpcio>=1.69.0
 	grpcio-tools>=1.69.0
 	pytest-grpc>=0.8.0
-	mypy>=1.4.1
+	mypy>=1.7.0
 	mypy-extensions>=1.0.0
 	mypy-protobuf>=3.5.0
 	types-PyYAML>=6.0.12.11
@@ -52,11 +52,11 @@ testing =
 	types-urllib3>=1.26.25.13
 	flake8>=6.1.0
 	flake8-rst-docstrings>=0.3.0
-	tox>=3.24
+	tox>=4.24.1
 	sphinx>=5.3.0
 	sphinxcontrib-napoleon>=0.7
 	sphinx-rtd-theme>=1.1.1
-	twine>=4.0.2
+	twine>=6.1.0
 	build>=0.10.0
 
 [options.package_data]

gym_csle_stopping_game-0.8.2/src/gym_csle_stopping_game/__version__.py

@@ -0,0 +1 @@
+__version__ = '0.8.2'

{gym_csle_stopping_game-0.8.0 → gym_csle_stopping_game-0.8.2}/src/gym_csle_stopping_game/dao/stopping_game_config.py

@@ -11,9 +11,9 @@ class StoppingGameConfig(SimulationEnvInputConfig):
     """
 
     def __init__(self, env_name: str,
-                 T: npt.NDArray[Any], O: npt.NDArray[np.int_], Z: npt.NDArray[Any],
-                 R: npt.NDArray[Any], S: npt.NDArray[np.int_], A1: npt.NDArray[np.int_],
-                 A2: npt.NDArray[np.int_], L: int, R_INT: int, R_COST: int, R_SLA: int, R_ST: int,
+                 T: npt.NDArray[Any], O: npt.NDArray[np.int32], Z: npt.NDArray[Any],
+                 R: npt.NDArray[Any], S: npt.NDArray[np.int32], A1: npt.NDArray[np.int32],
+                 A2: npt.NDArray[np.int32], L: int, R_INT: int, R_COST: int, R_SLA: int, R_ST: int,
                  b1: npt.NDArray[np.float64],
                  save_dir: str, checkpoint_traces_freq: int, gamma: float = 1, compute_beliefs: bool = True,
                  save_trace: bool = True) -> None:

{gym_csle_stopping_game-0.8.0 → gym_csle_stopping_game-0.8.2}/src/gym_csle_stopping_game/envs/stopping_game_mdp_attacker_env.py

@@ -48,7 +48,7 @@ class StoppingGameMdpAttackerEnv(BaseEnv):
         self.reset()
         super().__init__()
 
-    def step(self, pi2: Union[npt.NDArray[Any], int, float, np.int_, np.float64]) \
+    def step(self, pi2: Union[npt.NDArray[Any], int, float, int, np.float64]) \
             -> Tuple[npt.NDArray[Any], int, bool, bool, Dict[str, Any]]:
         """
         Takes a step in the environment by executing the given action
@@ -56,7 +56,8 @@ class StoppingGameMdpAttackerEnv(BaseEnv):
         :param pi2: attacker stage policy
         :return: (obs, reward, terminated, truncated, info)
         """
-        if type(pi2) is int or type(pi2) is float or type(pi2) is np.int64 or type(pi2) is np.float64:
+        if (type(pi2) is int or type(pi2) is float or type(pi2) is np.int64 or type(pi2) is np.int32 # type: ignore
+                or type(pi2) is np.float64): # type: ignore
             a2 = pi2
             if self.latest_attacker_obs is None:
                 raise ValueError("Attacker observation is None")

{gym_csle_stopping_game-0.8.0 → gym_csle_stopping_game-0.8.2}/src/gym_csle_stopping_game/util/stopping_game_util.py

@@ -31,7 +31,7 @@ class StoppingGameUtil:
         return np.array([0, 1, 2])
 
     @staticmethod
-    def defender_actions() -> npt.NDArray[np.int_]:
+    def defender_actions() -> npt.NDArray[np.int32]:
         """
         Gets the action space of the defender
 
@@ -40,7 +40,7 @@ class StoppingGameUtil:
         return np.array([0, 1])
 
     @staticmethod
-    def attacker_actions() -> npt.NDArray[np.int_]:
+    def attacker_actions() -> npt.NDArray[np.int32]:
         """
         Gets the action space of the attacker
 
@@ -217,7 +217,7 @@ class StoppingGameUtil:
         return Z
 
     @staticmethod
-    def sample_next_state(T: npt.NDArray[Any], l: int, s: int, a1: int, a2: int, S: npt.NDArray[np.int_]) -> int:
+    def sample_next_state(T: npt.NDArray[Any], l: int, s: int, a1: int, a2: int, S: npt.NDArray[np.int32]) -> int:
         """
         Samples the next state
 
@@ -245,7 +245,7 @@ class StoppingGameUtil:
         return int(np.random.choice(np.arange(0, len(b1)), p=b1))
 
     @staticmethod
-    def sample_next_observation(Z: npt.NDArray[Any], s_prime: int, O: npt.NDArray[np.int_]) -> int:
+    def sample_next_observation(Z: npt.NDArray[Any], s_prime: int, O: npt.NDArray[np.int32]) -> int:
         """
         Samples the next observation
 
@@ -390,7 +390,7 @@ class StoppingGameUtil:
         return file_str
 
     @staticmethod
-    def reduce_T_attacker(T: npt.NDArray[np.float_], strategy: Policy) -> npt.NDArray[np.float_]:
+    def reduce_T_attacker(T: npt.NDArray[np.float64], strategy: Policy) -> npt.NDArray[np.float64]:
         """
         Reduces the transition tensor based on a given attacker strategy
 
@@ -415,7 +415,7 @@ class StoppingGameUtil:
         return reduced_T
 
     @staticmethod
-    def reduce_R_attacker(R: npt.NDArray[np.float_], strategy: Policy) -> npt.NDArray[np.float_]:
+    def reduce_R_attacker(R: npt.NDArray[np.float64], strategy: Policy) -> npt.NDArray[np.float64]:
         """
         Reduces the reward tensor based on a given attacker strategy
 
@@ -433,7 +433,7 @@ class StoppingGameUtil:
         return reduced_R
 
     @staticmethod
-    def reduce_Z_attacker(Z: npt.NDArray[np.float_], strategy: Policy) -> npt.NDArray[np.float_]:
+    def reduce_Z_attacker(Z: npt.NDArray[np.float64], strategy: Policy) -> npt.NDArray[np.float64]:
         """
         Reduces the observation tensor based on a given attacker strategy
 
@@ -450,7 +450,7 @@ class StoppingGameUtil:
         return reduced_Z
 
     @staticmethod
-    def reduce_T_defender(T: npt.NDArray[np.float_], strategy: Policy) -> npt.NDArray[np.float_]:
+    def reduce_T_defender(T: npt.NDArray[np.float64], strategy: Policy) -> npt.NDArray[np.float64]:
         """
         Reduces the transition tensor based on a given defender strategy
 
@@ -469,7 +469,7 @@ class StoppingGameUtil:
         return reduced_T
 
     @staticmethod
-    def reduce_R_defender(R: npt.NDArray[np.float_], strategy: Policy) -> npt.NDArray[np.float_]:
+    def reduce_R_defender(R: npt.NDArray[np.float64], strategy: Policy) -> npt.NDArray[np.float64]:
         """
         Reduces the reward tensor based on a given defender strategy
 
@@ -487,10 +487,10 @@ class StoppingGameUtil:
         return reduced_R
 
     @staticmethod
-    def aggregate_belief_mdp_defender(aggregation_resolution: int, T: npt.NDArray[np.float_],
-                                      R: npt.NDArray[np.float_], Z: npt.NDArray[np.float_],
-                                      S: npt.NDArray[np.int_], A: npt.NDArray[np.int_], O: npt.NDArray[np.int_]) \
-            -> Tuple[npt.NDArray[np.float_], npt.NDArray[np.int_], npt.NDArray[np.float_], npt.NDArray[np.float_]]:
+    def aggregate_belief_mdp_defender(aggregation_resolution: int, T: npt.NDArray[np.float64],
+                                      R: npt.NDArray[np.float64], Z: npt.NDArray[np.float64],
+                                      S: npt.NDArray[np.int32], A: npt.NDArray[np.int32], O: npt.NDArray[np.int32]) \
+            -> Tuple[npt.NDArray[np.float64], npt.NDArray[np.int32], npt.NDArray[np.float64], npt.NDArray[np.float64]]:
         """
         Generates an aggregate belief MDP from a given POMDP specification and aggregation resolution
 
@@ -512,7 +512,7 @@ class StoppingGameUtil:
         return aggregate_belief_space, A, belief_T, belief_R
 
     @staticmethod
-    def generate_aggregate_belief_space(n: int, belief_space_dimension: int) -> npt.NDArray[np.float_]:
+    def generate_aggregate_belief_space(n: int, belief_space_dimension: int) -> npt.NDArray[np.float64]:
         """
         Generate an aggregate belief space B_n.
 
@@ -534,8 +534,8 @@ class StoppingGameUtil:
 
     @staticmethod
     def generate_aggregate_belief_reward_tensor(
-            aggregate_belief_space: npt.NDArray[np.float_], S: npt.NDArray[np.int_], A: npt.NDArray[np.int_],
-            R: npt.NDArray[np.float_]) -> npt.NDArray[np.float_]:
+            aggregate_belief_space: npt.NDArray[np.float64], S: npt.NDArray[np.int32], A: npt.NDArray[np.int32],
+            R: npt.NDArray[np.float64]) -> npt.NDArray[np.float64]:
         """
         Generates an aggregate reward tensor for the aggregate belief MDP
 
@@ -557,8 +557,9 @@ class StoppingGameUtil:
 
     @staticmethod
     def generate_aggregate_belief_transition_operator(
-            aggregate_belief_space: npt.NDArray[np.float_], S: npt.NDArray[np.int_], A: npt.NDArray[np.int_],
-            O: npt.NDArray[np.int_], T: npt.NDArray[np.float_], Z: npt.NDArray[np.float_]) -> npt.NDArray[np.float_]:
+            aggregate_belief_space: npt.NDArray[np.float64], S: npt.NDArray[np.int32], A: npt.NDArray[np.int32],
+            O: npt.NDArray[np.int32], T: npt.NDArray[np.float64], Z: npt.NDArray[np.float64]) \
+            -> npt.NDArray[np.float64]:
         """
         Generates an aggregate belief space transition operator
 
@@ -581,11 +582,11 @@ class StoppingGameUtil:
         return belief_T
 
     @staticmethod
-    def aggregate_belief_transition_probability(b1: npt.NDArray[np.float_], b2: npt.NDArray[np.float_], a: int,
-                                                S: npt.NDArray[np.int_], O: npt.NDArray[np.int_],
-                                                A: npt.NDArray[np.int_],
-                                                T: npt.NDArray[np.float_], Z: npt.NDArray[np.float_],
-                                                aggregate_belief_space: npt.NDArray[np.float_]) -> float:
+    def aggregate_belief_transition_probability(b1: npt.NDArray[np.float64], b2: npt.NDArray[np.float64], a: int,
+                                                S: npt.NDArray[np.int32], O: npt.NDArray[np.int32],
+                                                A: npt.NDArray[np.int32],
+                                                T: npt.NDArray[np.float64], Z: npt.NDArray[np.float64],
+                                                aggregate_belief_space: npt.NDArray[np.float64]) -> float:
         """
         Calculates the probability of transitioning from belief b1 to belief b2 when taking action a
 
@@ -615,9 +616,9 @@ class StoppingGameUtil:
         return prob
 
     @staticmethod
-    def pomdp_next_belief(o: int, a: int, b: npt.NDArray[np.float64], states: npt.NDArray[np.int_],
-                          observations: npt.NDArray[np.int_], observation_tensor: npt.NDArray[np.float_],
-                          transition_tensor: npt.NDArray[np.float_]) \
+    def pomdp_next_belief(o: int, a: int, b: npt.NDArray[np.float64], states: npt.NDArray[np.int32],
+                          observations: npt.NDArray[np.int32], observation_tensor: npt.NDArray[np.float64],
+                          transition_tensor: npt.NDArray[np.float64]) \
             -> npt.NDArray[np.float64]:
         """
         Computes the next belief of the POMDP using a Bayesian filter
@@ -642,9 +643,9 @@ class StoppingGameUtil:
         return np.array(b_prime)
 
     @staticmethod
-    def pomdp_bayes_filter(s_prime: int, o: int, a: int, b: npt.NDArray[np.float64], states: npt.NDArray[np.int_],
-                           observations: npt.NDArray[np.int_], observation_tensor: npt.NDArray[np.float_],
-                           transition_tensor: npt.NDArray[np.float_]) -> float:
+    def pomdp_bayes_filter(s_prime: int, o: int, a: int, b: npt.NDArray[np.float64], states: npt.NDArray[np.int32],
+                           observations: npt.NDArray[np.int32], observation_tensor: npt.NDArray[np.float64],
+                           transition_tensor: npt.NDArray[np.float64]) -> float:
         """
         A Bayesian filter to compute b[s_prime] of the POMDP
 
@@ -679,8 +680,8 @@ class StoppingGameUtil:
         return b_prime_s_prime
 
     @staticmethod
-    def find_nearest_neighbor_belief(belief_space: npt.NDArray[np.float_], target_belief: npt.NDArray[np.float_]) \
-            -> npt.NDArray[np.float_]:
+    def find_nearest_neighbor_belief(belief_space: npt.NDArray[np.float64], target_belief: npt.NDArray[np.float64]) \
+            -> npt.NDArray[np.float64]:
         """
         Finds the nearest neighbor (in the Euclidean sense) of a given belief in a certain belief space
 

{gym_csle_stopping_game-0.8.0 → gym_csle_stopping_game-0.8.2}/src/gym_csle_stopping_game.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-csle-stopping-game
-Version: 0.8.0
+Version: 0.8.2
 Summary: OpenAI gym reinforcement learning environment of a Dynkin (Optimal stopping) game in CSLE
 Author: Kim Hammar
 Author-email: hammar.kim@gmail.com
@@ -204,11 +204,11 @@ Classifier: Intended Audience :: Science/Research
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 Requires-Dist: gymnasium>=0.27.1
-Requires-Dist: csle-base>=0.8.0
-Requires-Dist: csle-common>=0.8.0
-Requires-Dist: csle-attacker>=0.8.0
-Requires-Dist: csle-defender>=0.8.0
-Requires-Dist: csle-collector>=0.8.0
+Requires-Dist: csle-base>=0.8.2
+Requires-Dist: csle-common>=0.8.2
+Requires-Dist: csle-attacker>=0.8.2
+Requires-Dist: csle-defender>=0.8.2
+Requires-Dist: csle-collector>=0.8.2
 Provides-Extra: test
 Requires-Dist: pytest>=6.0; extra == "test"
 Requires-Dist: pytest-cov>=2.0; extra == "test"
@@ -216,7 +216,7 @@ Requires-Dist: pytest-mock>=3.6.0; extra == "test"
 Requires-Dist: pytest-grpc>=0.8.0; extra == "test"
 Requires-Dist: grpcio>=1.69.0; extra == "test"
 Requires-Dist: grpcio-tools>=1.69.0; extra == "test"
-Requires-Dist: mypy>=1.4.1; extra == "test"
+Requires-Dist: mypy>=1.7.0; extra == "test"
 Requires-Dist: mypy-extensions>=1.0.0; extra == "test"
 Requires-Dist: mypy-protobuf>=3.5.0; extra == "test"
 Requires-Dist: types-PyYAML>=6.0.12.11; extra == "test"
@@ -226,11 +226,11 @@ Requires-Dist: types-requests>=2.31.0.1; extra == "test"
 Requires-Dist: types-urllib3>=1.26.25.13; extra == "test"
 Requires-Dist: flake8>=6.1.0; extra == "test"
 Requires-Dist: flake8-rst-docstrings>=0.3.0; extra == "test"
-Requires-Dist: tox>=3.24; extra == "test"
+Requires-Dist: tox>=4.24.1; extra == "test"
 Requires-Dist: sphinx>=5.3.0; extra == "test"
 Requires-Dist: sphinxcontrib-napoleon>=0.7; extra == "test"
 Requires-Dist: sphinx-rtd-theme>=1.1.1; extra == "test"
-Requires-Dist: twine>=4.0.2; extra == "test"
+Requires-Dist: twine>=6.1.0; extra == "test"
 Requires-Dist: build>=0.10.0; extra == "test"
 
 # `gym-csle-stopping-game`

{gym_csle_stopping_game-0.8.0 → gym_csle_stopping_game-0.8.2}/src/gym_csle_stopping_game.egg-info/requires.txt

@@ -1,9 +1,9 @@
 gymnasium>=0.27.1
-csle-base>=0.8.0
-csle-common>=0.8.0
-csle-attacker>=0.8.0
-csle-defender>=0.8.0
-csle-collector>=0.8.0
+csle-base>=0.8.2
+csle-common>=0.8.2
+csle-attacker>=0.8.2
+csle-defender>=0.8.2
+csle-collector>=0.8.2
 
 [test]
 pytest>=6.0
@@ -12,7 +12,7 @@ pytest-mock>=3.6.0
 pytest-grpc>=0.8.0
 grpcio>=1.69.0
 grpcio-tools>=1.69.0
-mypy>=1.4.1
+mypy>=1.7.0
 mypy-extensions>=1.0.0
 mypy-protobuf>=3.5.0
 types-PyYAML>=6.0.12.11
@@ -22,9 +22,9 @@ types-requests>=2.31.0.1
 types-urllib3>=1.26.25.13
 flake8>=6.1.0
 flake8-rst-docstrings>=0.3.0
-tox>=3.24
+tox>=4.24.1
 sphinx>=5.3.0
 sphinxcontrib-napoleon>=0.7
 sphinx-rtd-theme>=1.1.1
-twine>=4.0.2
+twine>=6.1.0
 build>=0.10.0

gym_csle_stopping_game-0.8.0/src/gym_csle_stopping_game/__version__.py

@@ -1 +0,0 @@
-__version__ = '0.8.0'